Skip to content
AI News HubLIVE
Original source2 min read

Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies

Summary

The paper proposes CAST (Certified Action Selection at Test time), which samples action chunks from a frozen diffusion policy, certifies each with a barrier condition, and executes the certified chunk ranked highest by a learned value ensemble. It also introduces viability estimation to avoid dead ends that one-step certification cannot see, improving joint task-and-constraint success across multiple robotic platforms.

SourcearXiv RoboticsAuthor: Angelo Moroncelli, Loris Roveda
Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 14 Nov 2026]

Title:Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies

View a PDF of the paper titled Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies, by Angelo Moroncelli and 1 other authors

View PDF HTML (experimental)

Abstract:Diffusion policies, which generate short action sequences by denoising random noise, are a leading way to learn robot skills from demonstrations. Once deployed, they meet constraints the demonstrations never contained, and retraining for each is impractical. A safety filter edits the policy's action to satisfy them, but the edit ignores the task, and a large edit can leave the policy where it cannot continue. We propose CAST (Certified Action Selection at Test time): draw a few action chunks from the frozen policy, certify each with a barrier condition, and execute the certified chunk that a learned value ensemble ranks highest. We prove that a certified step is safe whatever the critic does; that, whenever a certified sample exists, the executed chunk stays within log N nats of the policy conditioned on feasibility, while a safety-filter projection can be singular to it; and that an exact closed-loop identity splits the gain of ranking into availability, spread and the critic's target. Certifying the next chunk is not enough: a generative controller can have safe actions available now and none later. We characterise the safe control authority of a frozen policy under finite sampling, and CAST-V preserves it through a policy-conditioned viability, estimated with a model under a finite-sample guarantee or learned from the controller's own logs (CAST-VL). On robomimic manipulation, a planar quadrotor, a MuJoCo humanoid and a unicycle, with frozen policies, CAST raises joint task-and-constraint success above the output filter in nearly every setting; certifying before ranking is decisive where a filter's edit is large, and viability removes most dead ends that one-step certification cannot see. Project page: this https URL.

Comments: Under review

Subjects:

Robotics (cs.RO); Machine Learning (cs.LG); Systems and Control (eess.SY)

Cite as: arXiv:2611.19047 [cs.RO]

(or arXiv:2611.19047v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.19047

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Angelo Moroncelli [view email] [v1] Sat, 14 Nov 2026 00:44:27 UTC (2,990 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies, by Angelo Moroncelli and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs cs.LG cs.SY eess eess.SY

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • CAST samples action chunks from a frozen policy, certifies safety before ranking by learned value, avoiding large safety-filter edits that leave the policy unable to continue.
  • Theoretical results show certified steps are safe regardless of the critic, and the executed chunk stays within log N nats of the feasible-conditioned policy, while filter projection can be singular.
  • CAST-V/CAST-VL estimate policy-conditioned viability via a model with finite-sample guarantees or from controller logs, removing dead ends missed by one-step certification.
  • On robomimic manipulation, a planar quadrotor, a MuJoCo humanoid, and a unicycle, CAST outperforms output filters in nearly every setting.

Highlights and analysis are generated automatically and may contain errors. Check the original source.